Robust Real-Time Curb Detection for Autonomous Sanitation Vehicles

Yichao Cai1; Kejun Ou1; Dachuan Li2; Yuanfang Zhang1; Xiao Zhou3; Xingang Mou3

10.1109/ICUS58632.2023.10318292

2023

2023 IEEE International Conference on Unmanned Systems (ICUS)

2771-7364

979-8-3503-1631-5

2023 IEEE International Conference on Unmanned Systems (ICUS)

475-481

13-15 Oct. 2023

Hefei, China

Curb detection is a key enabling functionality for the precise curb-following sanitation control of autonomous sanitation vehicles. The robust and efficient curb detection in complex environments is still a challenging issue. In this paper, we propose a novel semantic segmentation-based framework for curb detection using monocular bird's eye-view images. We employ a lightweight segmentation network based on HRNet to extract the drivable area. A zero-shot post-processing approach is proposed to extract a candidate point set from the segmented image for robust curve fitting. In addition, we propose a modified RANSAC fitting approach that accounts for outlier points to achieve dynamic order curve fitting and curb representation. Experimental results in complex sanitation scenarios demonstrate the efficiency, accuracy, and robustness of the proposed approach.

Autonomous Sanitation Vehicles Curb Detection Semantic Segmentation Curve Fitting

通讯

EI

20235115260366

Complex Networks ; Sanitation ; Semantic Segmentation ; Semantics ; Zero-shot Learning

Environmental Engineering, General:454.1 ; Computer Systems And Equipment:722 ; Artificial Intelligence:723.4 ; Numerical Methods:921.6

IEEE

1.Research and Development Center, Autocity (Shenzhen) Autonomous Driving Co., Ltd., Shenzhen, China
2.Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China
3.School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan, China

Yichao Cai,Kejun Ou,Dachuan Li,et al. Robust Real-Time Curb Detection for Autonomous Sanitation Vehicles[C],2023:475-481.